Improving recommendations in tag-based systems with spectral clustering of tag neighbors

Publication Type:
Conference Proceeding
Lecture Notes in Electrical Engineering, 2012, 114 LNEE pp. 355 - 364
Issue Date:
Full metadata record
Files in This Item:
Filename Description Size
Pan Rong 2010.pdfPublished version1.73 MB
Adobe PDF
Tag as a useful metadata reflects the collaborative and conceptual features of documents in social collaborative annotation systems. In this paper, we propose a collaborative approach for expanding tag neighbors and investigate the spectral clustering algorithm to filter out noisy tag neighbors in order to get appropriate recommendation for users. The preliminary experiments have been conducted on MovieLens dataset to compare our proposed approach with the traditional collaborative filtering recommendation approach and naive tag neighbors expansion approach in terms of precision, and the result demonstrates that our approach could considerably improve the performance of recommendations. © 2012 Springer Science+Business Media B.V.
Please use this identifier to cite or link to this item: